© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129287
    Prev
    Next
    INDEX
    Explanations

    either X or Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commencing
    -0.06
    重要な
    -0.06
     commencent
    -0.06
     começando
    -0.06
     három
    -0.06
     वग
    -0.06
     شروع
    -0.06
    EDIT
    -0.06
     czter
    -0.06
     dört
    -0.06
    POSITIVE LOGITS
     wielu
    0.06
     പല
    0.06
     разными
    0.06
     여러
    0.06
     verschillende
    0.06
    Viele
    0.06
     do
    0.06
     Either
    0.06
     entweder
    0.06
     rav
    0.06
    Activations Density 0.001%

    No Known Activations